VulnSea

ai_inference_server vulnerabilities

CVEs whose affected-version data names the ai_inference_server package (pip). Each record lists the affected and patched versions; check a specific version with the dependency checker or POST /api/sbom.

72 CVEsRSS

CVE-2026-26209Medium· 5.5⚖ disputed
6mo ago

cbor2: cbor2: Denial of Service due to uncontrolled recursion via crafted CBOR payloads (CVE-2026-26209)

A flaw was found in cbor2, a library for encoding and decoding Concise Binary Object Representation (CBOR) data. A remote attacker can exploit this vulnerability by sending a specially crafted CBOR payload containing deeply nested structur…

▾ SunlitRed Hat · Red Hat Enterprise Linux AI (RHEL AI) 3EPSS 0.65%via CSAF
CVE-2026-30922High· 7.5PoC
6mo ago

pyasn1: pyasn1 Vulnerable to Denial of Service via Unbounded Recursion (CVE-2026-30922)

An unbounded recursion flaw has been discovered in the pypi pyasn1 library. This uncontrolled recursion occurs when decoding ASN.1 data with deeply nested structures. An attacker can supply a crafted payload containing nested SEQUENCE (0x3…

▾ MidnightRed Hat · Red Hat Enterprise Linux AppStream (v. 10)EPSS 0.93%via CSAF
CVE-2026-22701Medium· 5.3
8mo ago

filelock: filelock Time-of-Check-Time-of-Use (TOCTOU) in SoftFileLock (CVE-2026-22701)

A Time-of-Check-Time-of-Use (TOCTOU) flaw has been discovered in the pypi filelock package. The TOCTOU race condition vulnerability exists in the SoftFileLock implementation of the filelock package. An attacker with local filesystem access…

▾ SunlitRed Hat · Red Hat Ansible Automation Platform 2EPSS 0.13%via CSAF
CVE-2025-69227High· 7.5
8mo ago

aiohttp: aiohttp: Denial of Service via specially crafted POST request (CVE-2025-69227)

A flaw was found in aiohttp, an asynchronous HTTP client/server framework for Python. A remote attacker could exploit this vulnerability by sending a specially crafted POST request to an application using the Request.post() method, provide…

▾ TwilightRed Hat · Red Hat Ansible Automation Platform 2EPSS 0.39%via CSAF
CVE-2025-69228Medium· 6.8
8mo ago

aiohttp: aiohttp: Denial of Service via memory exhaustion from crafted POST request (CVE-2025-69228)

A flaw was found in aiohttp. A remote attacker can craft a malicious request that, when processed by an aiohttp server using the `Request.post()` method, causes the server's memory to fill uncontrollably. This can lead to a Denial of Servi…

▾ SunlitRed Hat · Red Hat OpenShift AI (RHOAI)EPSS 0.40%via CSAF
CVE-2025-66448High· 7.5
9mo ago

vllm: vLLM: Remote Code Execution via malicious model configuration (CVE-2025-66448)

A remote code execution vulnerability has been identified in vLLM. An attacker can exploit a weakness in the model loading process to silently fetch and run unauthorized, malicious Python code on the host system. This happens because the e…

▾ TwilightRed Hat · Red Hat OpenShift AI 3.3EPSS 0.66%via CSAF
CVE-2025-62426Medium· 6.5
10mo ago

vllm: vLLM vulnerable to DoS via large Chat Completion or Tokenization requests with specially crafted `chat_template_kwargs` (CVE-2025-624…

A vulnerability in vLLM allows an authenticated user to trigger unintended tokenization during chat template processing by supplying crafted chat_template_kwargs to the /v1/chat/completions or /tokenize endpoints. By forcing the server to …

▾ SunlitRed Hat · Red Hat Enterprise Linux AI (RHEL AI)EPSS 0.37%via CSAF
CVE-2025-59425High· 7.5
11mo ago

vllm: Timing Attack in vLLM API Token Verification Leading to Authentication Bypass (CVE-2025-59425)

A flaw was found in vLLM’s API token authentication logic, where token comparisons were not performed in constant time. This weakness could allow an attacker to exploit timing differences to guess valid tokens and bypass authentication.

▾ TwilightRed Hat · Red Hat OpenShift AI 3.3EPSS 0.57%via CSAF
CVE-2025-48956High· 7.5
1y ago

vllm: HTTP header size limit not enforced allows Denial of Service from Unauthenticated requests (CVE-2025-48956)

A flaw was found in vLLM. A denial of service (DoS) vulnerability can be triggered by sending a single HTTP GET request with an extremely large X-Forwarded-For header to an HTTP endpoint. This results in server memory exhaustion, potential…

▾ TwilightRed Hat · Red Hat Enterprise Linux AI (RHEL AI)EPSS 0.56%via CSAF
CVE-2025-57809High· 7.5
1y ago

xgrammar: XGrammar affected by Denial of Service by infinite recursion grammars (CVE-2025-57809)

A flaw was found in xgrammar. Recursive grammar definitions could trigger infinite recursion during parsing in GrammarMatcherBase::ExpandEquivalentStackElements, leading to unbounded stack growth and a segmentation fault. This vulnerabilit…

▾ TwilightRed Hat · Red Hat Enterprise Linux AI 1.5EPSS 0.47%via CSAF
CVE-2025-50181Medium· 5.3
1y ago

urllib3: urllib3 redirects are not disabled when retries are disabled on PoolManager instantiation (CVE-2025-50181)

A flaw was found in urllib3. The `PoolManager` class allows redirects to be disabled by configuring retries in a specific manner, effectively bypassing intended HTTP redirection behavior. A network attacker can leverage this configuration …

▾ SunlitRed Hat · Red Hat Enterprise Linux 9EPSS 0.47%via CSAF
CVE-2025-50182Medium· 5.3
1y ago

urllib3: urllib3 does not control redirects in browsers and Node.js (CVE-2025-50182)

A flaw was found in urllib3. The library fails to properly validate redirect URLs, allowing an attacker to manipulate redirect chains when used in environments like Pyodide utilizing the JavaScript Fetch API. This lack of validation can en…

▾ SunlitRed Hat · Red Hat Enterprise Linux 9EPSS 0.39%via CSAF
ai_inference_server vulnerabilities (CVEs) — page 3 · VulnSea